mcp-supabase
Execute database operations via Supabase MCP (query/write/migration/logs/type generation). Triggers:…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,664 results
agent-instruction-hygiene
Review AGENTS.md, CLAUDE.md, and `.agents/skills` for instruction sprawl, duplicated guidance, routing overlap, and misplaced process detail. Use when adding…
neqsim-ccs-hydrogen
CO2 capture, transport, storage (CCS) and hydrogen systems patterns for NeqSim. USE WHEN: modeling CO2 pipelines, injection wells, impurity effects on phase…
herdr-operations
Use when inspecting or operating Herdr sessions, workspaces, tabs, panes, agents, terminal output, agent messaging, or waits.
skill-creator
Create, review, and improve skills for Pi agents. A skill is a folder with a SKILL.md that teaches an agent specialized workflows, domain knowledge, or tool…
rag-search
Search the knowledge base for relevant documents. Use when the user wants to find documents in their indexed corpus, has questions that could be answered by…
rag-tracking
External persistent memory for document ingestion and issues, designed for agents without built-in memory (Claude Code, Codex, OpenCode). Use when ingesting…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an…
tutorial
Interactive guided tutorial for ExoPriors/Scry. Walks a human+agent pair through their first Scry session: schema discovery, lexical search, semantic…
abm-campaign
ABM campaign skill for Claude Code: run a full Account-Based Marketing campaign end-to-end — from ICP definition to live LinkedIn Ads. Builds targeted account…
hubspot-enrichment-scoring
HubSpot CRM enrichment and lead scoring skill for Claude Code and Codex: pull companies from HubSpot, match and enrich them via Vibe Prospecting with…
talent-mapping
Talent mapping skill for Claude Code and Codex: map the talent bench for a function across a set of target or competitor companies using Explorium data via…
talent-sourcing
Talent sourcing skill for Claude Code and Codex: turn a job description or role brief into a ranked candidate pipeline using real-time professional and company…
prompt engineering skill
Craft effective prompts that get the best results from language models.
mcp-expert
Expert in Model Context Protocol (MCP) server development. Use when building MCP servers, creating tools for Claude, implementing resources, debugging MCP…
triage
Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
ai-sdk-5
Vercel AI SDK 5 patterns: useChat, streaming, tool integration, Server Actions. Trigger: When building AI chat interfaces, using Vercel AI SDK, streaming LLM…
autonomous-vps
Stack-agnostic METHOD for an invoked (not unattended) AI agent to develop, deploy, and administer projects on a self-hosted VPS with contained blast radius —…
backlog
A stack-agnostic, storage-agnostic METHOD for keeping a backlog STRUCTURALLY HEALTHY. Its axis is INTEGRITY — not where the backlog lives; it works the same on…
backlog-as-code
Local storage adapter that materializes and authors a versioned markdown backlog at docs/BACKLOG.md. Four sub-flows: /backlog-file-init (materialize the file…
claude-folder-audit
Audits the ~/.claude/ runtime folder or a project's .claude/ configuration for installation drift, skill deployment gaps, orphaned artifacts, and scope tier…
harness-engineering
Engineering reference for the Claude Code agent harness — the operating environment around the model: hooks, tools & permissions, MCP servers, subagents,…
orchestrator-status
Returns current orchestrator state: active SDD changes, loaded skills, configuration source, classification enabled/disabled
project-claude-organizer
Reads the project .claude/ folder, compares observed contents against the canonical SDD structure, presents a dry-run reorganization plan, and applies it…